Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

W&B: Update Tables API and comply with new dataset_check #3772

Merged
merged 3 commits into from
Jun 25, 2021
Merged

W&B: Update Tables API and comply with new dataset_check #3772

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a1d3106
Update tables API and windows path fix
AyushExel Jun 21, 2021
c22d56c
Merge branch 'ultralytics:master' into wandb
AyushExel Jun 25, 2021
a013a2f
update dataset check
AyushExel Jun 25, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 11 additions & 6 deletions utils/wandb_logging/wandb_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -136,7 +136,6 @@ def __init__(self, opt, name, run_id, data_dict, job_type='Training'):

def check_and_upload_dataset(self, opt):
assert wandb, 'Install wandb to upload dataset'
check_dataset(self.data_dict)
config_path = self.log_dataset_artifact(check_file(opt.data),
opt.single_cls,
'YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem)
Expand Down Expand Up @@ -171,17 +170,19 @@ def setup_training(self, opt, data_dict):
data_dict['val'] = str(val_path)
self.val_table = self.val_artifact.get("val")
self.map_val_table_path()
wandb.log({"validation dataset": self.val_table})

if self.val_artifact is not None:
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
self.result_table = wandb.Table(["epoch", "id", "prediction", "avg_confidence"])
self.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
if opt.bbox_interval == -1:
self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1
return data_dict

def download_dataset_artifact(self, path, alias):
if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX):
artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias)
dataset_artifact = wandb.use_artifact(artifact_path.as_posix())
dataset_artifact = wandb.use_artifact(artifact_path.as_posix().replace("\\","/"))
assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'"
datadir = dataset_artifact.download()
return datadir, dataset_artifact
Expand Down Expand Up @@ -216,6 +217,7 @@ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
with open(data_file) as f:
data = yaml.safe_load(f) # data dict
check_dataset(data)
nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])
names = {k: v for k, v in enumerate(names)} # to index dictionary
self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(
Expand All @@ -228,6 +230,7 @@ def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=
data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val')
path = data_file if overwrite_config else '_wandb.'.join(data_file.rsplit('.', 1)) # updated data.yaml path
data.pop('download', None)
data.pop('path', None)
with open(path, 'w') as f:
yaml.safe_dump(data, f)

Expand Down Expand Up @@ -297,6 +300,7 @@ def log_training_progress(self, predn, path, names):
id = self.val_table_map[Path(path).name]
self.result_table.add_data(self.current_epoch,
id,
self.val_table.data[id][1],
wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set),
total_conf / max(1, len(box_data))
)
Expand All @@ -312,11 +316,12 @@ def end_epoch(self, best_result=False):
wandb.log(self.log_dict)
self.log_dict = {}
if self.result_artifact:
train_results = wandb.JoinedTable(self.val_table, self.result_table, "id")
self.result_artifact.add(train_results, 'result')
self.result_artifact.add(self.result_table, 'result')
wandb.log_artifact(self.result_artifact, aliases=['latest', 'last', 'epoch ' + str(self.current_epoch),
('best' if best_result else '')])
self.result_table = wandb.Table(["epoch", "id", "prediction", "avg_confidence"])

wandb.log({"evaluation": self.result_table})
self.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")

def finish_run(self):
Expand Down